Capraru, R., Lupu, E., Wang, J.-G., & Soong, B. H. (2026). Leveraging Adverse Weather for Enhanced LiDAR Spoofing in Autonomous Driving: Challenges and Opportunities. IEEE Vehicular Technology Magazine, 2–12. https://doi.org/10.1109/mvt.2025.3648068
Abstract:
LIDAR-based 3D perception systems are critical for
autonomous vehicle (AV) navigation, yet they remain
vulnerable to spoofing attacks that can create false
detections (ghost objects) or hide real obstacles. Despite
significant advances in object detection, existing methods
remain highly susceptible to adversarial attacks. Furthermore,
existing research has largely overlooked the impact of weather
conditions on both attacks and defences. No existing study
provides a systematic analysis on how the rain effect affects
spoofing and hiding attacks. Motivated by this critical gap,
we propose a novel rain-aware threat model in this paper,
focusing on LiDAR spoofing attacks involving object insertion
(ghost objects) and removal (hiding attacks). We review stateof-
the-art attack implementations and emphasize how rain
increases attack feasibility and stealth, enabling attackers to
achieve effective spoofing with significantly fewer perturbed
points. We call this a reduced attack budget. Formally, we
define the attack budget as the minimal number of spoofed
points (and corresponding laser returns) needed to meet attack
success (ghost insertion: high confidence false positives;
object hiding: low confidence false negatives). Additionally,
we assess current LiDAR-specific defenses, highlighting their
limitations in rainy conditions. By analyzing recent advances
using both simulated and real data, we expose vulnerabilities
intensified by adverse weather and propose future research
directions to enhance AV resilience against LiDAR spoofing
attacks. Our contribution is a unified, rain-aware threat
model that: (i) formalizes how rain reshapes LiDAR returns
and attacker/defender constraints, (ii) predicts when physicalinvariant
and temporal defenses fail, and (iii) analyses the
attack budgets required, insights not available from prior
single-paper case studies. We also introduce a simulation
benchmark under our controlled setup that tabulates attack
success and minimal point budgets across light/medium/heavy
rain and low/high-resolution LiDARs.